Systems and methods for updating navigational maps

Abstract

Systems and methods for updating navigational maps based using at least one sensor are provided. In one aspect, a control system for an autonomous vehicle, includes a processor and a computer-readable memory configured to cause the processor to: receive output from at least one sensor located on the autonomous vehicle indicative of a driving environment of the autonomous vehicle, retrieve a navigational map used for driving the autonomous vehicle, and detect one or more inconsistencies between the output of the at least one sensor and the navigational map. The computer-readable memory is further configured to cause the processor to: in response to detecting the one or more inconsistencies, trigger mapping of the driving environment based on the output of the at least one sensor, update the navigational map based on the mapped driving environment, and drive the autonomous vehicle using the updated navigational map.

What is claimed is: 
     
       1. A control system for an autonomous vehicle, comprising:
 a processor; and 
 a computer-readable memory in communication with the processor and having stored thereon computer-executable instructions to cause the processor to:
 receive output from at least one sensor located on the autonomous vehicle indicative of a driving environment of the autonomous vehicle, 
 retrieve a navigational map used for driving the autonomous vehicle, 
 detect one or more inconsistencies between the output of the at least one sensor and the navigational map, 
 detect one or more calibration inconsistencies in the output of the at least one sensor, the one or more calibration inconsistencies being between the at least one sensor and a second sensor, 
 determine whether the one or more inconsistencies between the output of the at least one sensor and the navigational map are due to the detected one or more calibration inconsistencies, 
 in response to detecting the one or more inconsistencies, trigger mapping of the driving environment based on the output of the at least one sensor if the one or more inconsistencies are not due to the detected one or more calibration inconsistencies, 
 update the navigational map based on the mapped driving environment, and 
 drive the autonomous vehicle using the updated navigational map. 
 
 
     
     
       2. The control system of  claim 1 , wherein the detecting of the one or more inconsistencies is performed using an anomaly detection module and the mapping of the driving environment is performed using a real-time mapping module, and wherein the real-time mapping module is more computationally intensive than the anomaly detection module. 
     
     
       3. The control system of  claim 1 , wherein the triggering of the mapping of the driving environment is further in response to determining that a number of the one or more inconsistencies is greater than a threshold number of inconsistencies. 
     
     
       4. The control system of  claim 3 , wherein the memory further has stored thereon computer-executable instructions to cause the processor to:
 refrain from triggering the mapping of the driving environment in response to the number of the one or more inconsistencies being less than the threshold number of inconsistencies, and 
 drive the autonomous vehicle using the retrieved navigational map. 
 
     
     
       5. The control system of  claim 1 , wherein the memory further has stored thereon computer-executable instructions to cause the processor to:
 determine whether the mapping of the driving environment has generated sufficient new map data for the updating of the navigational map. 
 
     
     
       6. The control system of  claim 5 , wherein the determination of whether the mapping of the driving environment has generated sufficient new map data comprises:
 determining a first parameter including a measurement of consistency between the new map data and the navigational map, and 
 determining a second parameter indicative of whether the new map data provides sufficient drivable space for the autonomous vehicle. 
 
     
     
       7. The control system of  claim 6 , wherein the determination of whether the mapping of the driving environment has generated sufficient new map data comprises:
 comparing the first parameter to a first parameter threshold, 
 comparing the second parameter to a second parameter threshold, and 
 determining that the mapping of the driving environment has generated the sufficient new map data in response to the first parameter being greater than the first parameter threshold and the second parameter being greater than the second parameter threshold. 
 
     
     
       8. The control system of  claim 7 , wherein the determination of whether the mapping of the driving environment has generated sufficient new map data comprises:
 determining that the mapping of the driving environment has not generated the sufficient new map data in response to at least one of: the first parameter being less than the first parameter threshold and the second parameter being less than the second parameter threshold, and 
 continuing the mapping of the driving environment based on the output of the at least one sensor in response to the determining that the mapping of the driving environment has not generated the sufficient new map data. 
 
     
     
       9. A non-transitory computer readable storage medium having stored thereon instructions that, when executed, cause at least one computing device to:
 receive output from at least one sensor located on an autonomous vehicle indicative of a driving environment of the autonomous vehicle; 
 retrieve a navigational map used for driving the autonomous vehicle; 
 detect one or more inconsistencies between the output of the at least one sensor and the navigational map; 
 detect one or more calibration inconsistencies in the output of the at least one sensor, the one or more calibration inconsistencies being between the at least one sensor and a second sensor; 
 determine whether the one or more inconsistencies between the output of the at least one sensor and the navigational map are due to the detected one or more calibration inconsistencies; 
 in response to detecting the one or more inconsistencies, trigger mapping of the driving environment based on the output of the at least one sensor if the one or more inconsistencies are not due to the detected one or more calibration inconsistencies; 
 update the navigational map based on the mapped driving environment; and 
 drive the autonomous vehicle using the updated navigational map. 
 
     
     
       10. The non-transitory computer readable storage medium of  claim 9 , wherein the updating of the navigational map comprises:
 deleting one or more objects from the navigational map that correspond to the one or more inconsistencies. 
 
     
     
       11. The non-transitory computer readable storage medium of  claim 9 , wherein the non-transitory computer readable storage medium further has stored thereon instructions that, when executed, cause the at least one computing device to:
 provide the updated map to other autonomous vehicles over the air. 
 
     
     
       12. The non-transitory computer readable storage medium of  claim 9 , wherein the mapping of the driving environment comprises:
 identifying a lane based on the output from the at least one sensor, 
 detecting a ground painting within the lane, and 
 identifying a lane type for the lane based on the ground painting. 
 
     
     
       13. The non-transitory computer readable storage medium of  claim 9 , wherein the non-transitory computer readable storage medium further has stored thereon instructions that, when executed, cause the at least one computing device to:
 identify a sign indicative of construction ahead of the autonomous vehicle, and 
 reduce a threshold number of the inconsistencies required to trigger the mapping of the driving environment in response to identifying the sign indicative of the construction. 
 
     
     
       14. The non-transitory computer readable storage medium of  claim 13 , wherein the threshold number of the inconsistencies required to trigger the mapping of the driving environment is reduced for a predetermined length of time. 
     
     
       15. A method comprising:
 receiving output from at least one sensor located on an autonomous vehicle indicative of a driving environment of the autonomous vehicle; 
 retrieving a navigational map used for driving the autonomous vehicle; 
 detecting one or more inconsistencies between the output of the at least one sensor and the navigational map;
 detecting one or more calibration inconsistencies in the output of the at least one sensor, the one or more calibration inconsistencies being between the at least one sensor and a second sensor; 
 determining whether the one or more inconsistencies between the output of the at least one sensor and the navigational map are due to the detected one or more calibration inconsistencies; 
 
 in response to detecting the one or more inconsistencies, triggering mapping of the driving environment based on the output of the at least one sensor if the one or more inconsistencies are not due to the detected one or more calibration inconsistencies; 
 updating the navigational map based on the mapped driving environment; and 
 driving the autonomous vehicle using the updated navigational map. 
 
     
     
       16. The method of  claim 15 , further comprising:
 detecting a traffic light based on the output of the at least one sensor, and 
 determining a location of a stopping line based on the detected traffic light. 
 
     
     
       17. The method of  claim 15 , wherein the at least one sensor comprises one or more of: a camera, a LIDAR, a global positioning system GPS, and inertial measurement unit (IMU), a RADAR, and a speedometer. 
     
     
       18. The method of  claim 15 , wherein the mapping of the driving environment comprises one or more of:
 mapping one or more lanes of a roadway, 
 mapping one or more traffic signs, 
 mapping one or more traffic lights, and 
 mapping one or more ground paintings.